{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","short_pith_number":"pith:M3S3TIBB","canonical_record":{"source":{"id":"2607.10020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca1fad18a95c18b8a5bd59afa608234568313aed576389e140a596b6c9524637","abstract_canon_sha256":"59924e3b6bcb1909294d104aa76357788eb74af0f845594e52ea09c7d830cb32"},"schema_version":"1.0"},"canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","source":{"kind":"arxiv","id":"2607.10020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10020","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10020v1","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10020","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"M3S3TIBBJY6J","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"M3S3TIBBJY6JT3CN","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"M3S3TIBB","created_at":"2026-07-14T00:18:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca1fad18a95c18b8a5bd59afa608234568313aed576389e140a596b6c9524637","abstract_canon_sha256":"59924e3b6bcb1909294d104aa76357788eb74af0f845594e52ea09c7d830cb32"},"schema_version":"1.0"},"canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:47.931036Z","signature_b64":"sUWeW9eS0RtRDmPWLxWsKZ8/w7k6Rx96iJsvndGkBWRYmUsF+7jeWRCh+l8q98HV5HiMPcb4Ck66wQAPVcJdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","last_reissued_at":"2026-07-14T00:18:47.930255Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:47.930255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10020","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T00:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TlZFtPCbn13PG7RFBB3IYI75jFc/yFJRAaNdSQ+5ZRkX4qjsCgOQr/OY8uvAHUGkcdxDP9IqTzRlQUHEVgGuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:01:25.050680Z"},"content_sha256":"b7da124bd229572d536f0ecec0ebf206b40e8cb07e4a873e288b54315c29c96a","schema_version":"1.0","event_id":"sha256:b7da124bd229572d536f0ecec0ebf206b40e8cb07e4a873e288b54315c29c96a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lars Henry Berge Olsen, Mark Anderson, Martin Jullum, Pierre Lison","submitted_at":"2026-07-10T22:46:11Z","abstract_excerpt":"We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus. The tool builds on prior techniques for document fingerprinting, but extends them with a novel mechanism to explicitly capture sequences of matching fingerprints. By identifying such chains, the tool can more reliably detect near-verbatim copies of a given text rather than mere textual similarities. This makes FindMyText particularly suited for verifying the presence of copyrighted material in a corpus. Leveraging a distributed, disk-based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10020","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.10020/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T00:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qI61vVEtO5CbQVIvxn/PvtQOC08Mo1pTga6V7MF6yVqtiytNz6UFZ2K8egXVSog81olwcqNTYN7tvaVvHZqCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:01:25.051171Z"},"content_sha256":"50b5c39684796619e750720b63b557638fdec9008062587d80f71da0590858fb","schema_version":"1.0","event_id":"sha256:50b5c39684796619e750720b63b557638fdec9008062587d80f71da0590858fb"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","target":"integrity","payload":{"note":"Identifier '10.5555/3721488.3721804' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Sullivan, Dakota and Mutlu, Bilge. Protecting User Data Through Privacy-Sensitive Robot Design. Proceedings of the 2025 ACM/IEEE International Conference on Human-Robot Interaction. doi:10.5555/3721488.3721804","arxiv_id":"2607.10020","detector":"doi_compliance","evidence":{"doi":"10.5555/3721488.3721804","arxiv_id":null,"ref_index":81,"raw_excerpt":"Sullivan, Dakota and Mutlu, Bilge. Protecting User Data Through Privacy-Sensitive Robot Design. Proceedings of the 2025 ACM/IEEE International Conference on Human-Robot Interaction. doi:10.5555/3721488.3721804","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":81,"audited_at":"2026-07-14T01:02:56.113619Z","event_type":"pith.integrity.v1","detected_doi":"10.5555/3721488.3721804","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"9066c8ea25287a977b1bcbc45210c654fedeb17fccacf9af60fff26bb9a34be1","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":13093,"payload_sha256":"c5b7a8505b291d6668e869bf5362427654e1abda38dc055d60f681f526ed02cb","signature_b64":"RAlhxruElxLgjhT8u260X4lGWdY3QqYdJEkTepiQxgHWc+WW2NEe2HsWM8K2uG0J1TzY0gqbd+SEje7bypwsCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuzCcizruC2jSoNzGXTXi8MF0UcpZ2cPYluJPrldFoyp2txWeD8qELrjKE+M0SWzVz51uLlaFMaJ3onNDOfRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:01:25.054786Z"},"content_sha256":"a0d3ae142430c5082b301c2490b17838e636905b7fdcd7d25ac948c95c8bcc07","schema_version":"1.0","event_id":"sha256:a0d3ae142430c5082b301c2490b17838e636905b7fdcd7d25ac948c95c8bcc07"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1162/grey\\_a\\_00389) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Crawford, Kate and Schultz, Jason. The work of copyright law in the age of generative AI. Grey room. doi:10.1162/grey\\_a\\_00389","arxiv_id":"2607.10020","detector":"doi_compliance","evidence":{"ref_index":73,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Crawford, Kate and Schultz, Jason. The work of copyright law in the age of generative AI. Grey room. doi:10.1162/grey\\_a\\_00389","reconstructed_doi":"10.1162/grey\\_a\\_00389"},"severity":"advisory","ref_index":73,"audited_at":"2026-07-14T01:02:56.113619Z","event_type":"pith.integrity.v1","detected_doi":"10.1162/grey\\_a\\_00389","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"7d546c6830225d325883313a7b539208b554d9fd995208abad26056b26031f1d","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":13092,"payload_sha256":"f0a578bc5fbb2527158ad5cf2b5c5995ee20ef8e4f10b6511ff6b5dac1071cde","signature_b64":"JNbNYiRWsdM3y9oZOJg8l7PTow/tHp7yQ4hVb5bN3JOvWYCdCKqakO7TUyQOwPKIO71e+7CczeB9CZPuK6tSCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7TAlFbOX3qAQTe9NGhTYKE9VtpWPJltgR5YkuMCamTNxxao3yAFdnItT05jYQ/SrbKppxpoiP3Dz6VWcFAw6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:01:25.055162Z"},"content_sha256":"8ee4e88f39df952e043c5af73abbf5123d5adc87790ffa6a59e347cadda11b40","schema_version":"1.0","event_id":"sha256:8ee4e88f39df952e043c5af73abbf5123d5adc87790ffa6a59e347cadda11b40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/bundle.json","state_url":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T21:01:25Z","links":{"resolver":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5","bundle":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/bundle.json","state":"https://pith.science/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3S3TIBBJY6JT3CNBJSTXXLSA5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M3S3TIBBJY6JT3CNBJSTXXLSA5","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"59924e3b6bcb1909294d104aa76357788eb74af0f845594e52ea09c7d830cb32","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","title_canon_sha256":"ca1fad18a95c18b8a5bd59afa608234568313aed576389e140a596b6c9524637"},"schema_version":"1.0","source":{"id":"2607.10020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10020","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10020v1","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10020","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"M3S3TIBBJY6J","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"M3S3TIBBJY6JT3CN","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"M3S3TIBB","created_at":"2026-07-14T00:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:50b5c39684796619e750720b63b557638fdec9008062587d80f71da0590858fb","target":"graph","created_at":"2026-07-14T00:18:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.10020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus. The tool builds on prior techniques for document fingerprinting, but extends them with a novel mechanism to explicitly capture sequences of matching fingerprints. By identifying such chains, the tool can more reliably detect near-verbatim copies of a given text rather than mere textual similarities. This makes FindMyText particularly suited for verifying the presence of copyrighted material in a corpus. Leveraging a distributed, disk-based ","authors_text":"Lars Henry Berge Olsen, Mark Anderson, Martin Jullum, Pierre Lison","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","title":"Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10020","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b7da124bd229572d536f0ecec0ebf206b40e8cb07e4a873e288b54315c29c96a","target":"record","created_at":"2026-07-14T00:18:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"59924e3b6bcb1909294d104aa76357788eb74af0f845594e52ea09c7d830cb32","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T22:46:11Z","title_canon_sha256":"ca1fad18a95c18b8a5bd59afa608234568313aed576389e140a596b6c9524637"},"schema_version":"1.0","source":{"id":"2607.10020","kind":"arxiv","version":1}},"canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66e5b9a0214e3c99ec4d0a653bdd7207737ba3b93187dfce5718d70e6b7a5123","first_computed_at":"2026-07-14T00:18:47.930255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:47.930255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sUWeW9eS0RtRDmPWLxWsKZ8/w7k6Rx96iJsvndGkBWRYmUsF+7jeWRCh+l8q98HV5HiMPcb4Ck66wQAPVcJdDg==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:47.931036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10020","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:8ee4e88f39df952e043c5af73abbf5123d5adc87790ffa6a59e347cadda11b40","sha256:a0d3ae142430c5082b301c2490b17838e636905b7fdcd7d25ac948c95c8bcc07"]}],"invalid_events":[],"applied_event_ids":["sha256:b7da124bd229572d536f0ecec0ebf206b40e8cb07e4a873e288b54315c29c96a","sha256:50b5c39684796619e750720b63b557638fdec9008062587d80f71da0590858fb"],"state_sha256":"600ef788eb5257c33d8e4aa00e2759c7b8d2150bfb7185f00ffab0f64ec0b283"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XC9ke5VdeHCJeL54QfDczxgJfI3JSNV9h/ofxB4Zu3LQ5Y2usEB+Bu56n8rEyzP8/Rx5HJ0UyEyUW1v+0X2iBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T21:01:25.058095Z","bundle_sha256":"2614b42aa26a464ddeb1fe97763f2e47bf781c197603f23af9b81a4a428520c3"}}